Mamba Codestral 7B v0.1 needs ~7.2 GB VRAM. RX 6700 XT 12GB has 12.0 GB. With Q4_K_M quantization, expect ~54 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
53.8 tok/s
TTFT
3600 ms
Safe context
110K
Memory
7.2 GB / 12.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 53.8 tok/s | 1964 ms | 110K |
| Coding | C | Runs well | 53.8 tok/s | 3600 ms | 110K |
| Agentic Coding | C | Runs well | 53.8 tok/s | 5236 ms | 110K |
| Reasoning | C | Runs well | 53.8 tok/s | 4255 ms | 110K |
| RAG | C | Runs well | 53.8 tok/s | 6545 ms | 110K |
How Mamba Codestral 7B v0.1 (7B params) fits at each quantization level on RX 6700 XT 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | C49 |
Q3_K_S | 3 | 3.4 GB | Low | C49 |
NVFP4 | 4 |
Copy-paste commands to run Mamba Codestral 7B v0.1 on your machine.
Run
lms load hf-gabriellarson--mamba-codestral-7b-v0-1-gguf && lms server startYes, RX 6700 XT 12GB can run Mamba Codestral 7B v0.1 with a C grade (Runs well). Expected decode speed: 53.8 tok/s.
Mamba Codestral 7B v0.1 (7B parameters) requires approximately 7.2 GB of memory with Q4_K_M quantization.
The recommended quantization for Mamba Codestral 7B v0.1 is Q4_K_M, which balances quality and memory efficiency.
On RX 6700 XT 12GB, Mamba Codestral 7B v0.1 achieves approximately 53.8 tokens per second decode speed with a time-to-first-token of 3600ms using Q4_K_M quantization.
For coding workloads, Mamba Codestral 7B v0.1 on RX 6700 XT 12GB receives a C grade with 53.8 tok/s and 110K context.
On RX 6700 XT 12GB, Mamba Codestral 7B v0.1 can safely use up to 110K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-gabriellarson--mamba-codestral-7b-v0-1-gguf-on-rx-6700-xt-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
3.9 GB |
| Medium |
| C50 |
Q4_K_M | 4 | 4.3 GB | Medium | C51 |
Q5_K_M | 5 | 5.0 GB | High | C52 |
Q6_K | 6 | 5.7 GB | High | C52 |
Q8_0Best for your GPU | 8 | 7.5 GB | Very High | C51 |
F16 | 16 | 14.3 GB | Maximum | F0 |